Lilia Lazli ; Mohamed Tayeb Laskri - A New Data Fusion Method for Hybrid MMC/RNA Learning

arima:1842 - Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées, September 2, 2005, Volume 3, Special Issue CARI'04, november 2005 -
A New Data Fusion Method for Hybrid MMC/RNA Learning

Authors: Lilia Lazli ; Mohamed Tayeb Laskri

It is well known that traditional Hidden Markov Models (HMM) systems lead to a considerable improvement when more training data or more parameters are used. However, using more data with hybrid Hidden Markov Models and Artificial Neural Networks (HMM/ANN) models results in increased training times without improvements in performance. We developed in this work a new method based on automatically separating data into several sets and training several neural networks of Multi-Layer Perceptrons (MLP) type on each set. During the recognition phase, models are combined using several criteria (based on data fusion techniques) to provide the recognized word. We showed in this paper that this method significantly improved the recognition accuracy. This method was applied in an Arabic speech recognition system. This last is based on the one hand, on a fuzzy clustering (application of the fuzzy c-means algorithm) and of another share, on a segmentation at base of the genetic algorithms.

Volume: Volume 3, Special Issue CARI'04, november 2005
Published on: September 2, 2005
Submitted on: February 25, 2005
Keywords: data fusion method,artificial neural networks,hidden Markov models,Arabic speech recognition,fuzzy clustering,genetic algorithms,méthode de fusion de données.,modèles de Markov cachés,réseaux de neurones artificiels,algorithmes génétiques,Reconnaissance de la parole arabe,segmentation floue,[INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL],[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]


Consultation statistics

This page has been seen 148 times.
This article's PDF has been downloaded 442 times.